© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1075
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )(*
    -0.28
    )=='
    -0.26
    .AF
    -0.25
    )();↵
    -0.24
    ++;č↵č↵
    -0.24
    					↵					↵
    -0.24
    ;č↵č↵č↵č↵
    -0.24
    "text
    -0.23
    ,},↵
    -0.23
    Nguá»ĵn
    -0.23
    POSITIVE LOGITS
    0.29
    0.29
    FormsModule
    0.28
    0.27
    0.26
    0.26
     sublic
    0.25
    oriously
    0.25
    家éĥ½çŁ¥éģĵ
    0.25
    !I
    0.24
    Activations Density 0.723%

    No Known Activations